Method for Training Convolution Neural Network With Multiple Classifiers [适用于具有多分类器的卷积神经网络训练方法] - 文章详情页

作者：

Li, J. (Li, J..) | Li, L. (Li, L..) | Zhang, Y. (Zhang, Y..) (学者：张勇) | Wang, P. (Wang, P..) | Zuo, G. (Zuo, G..)

收录：

Scopus PKU CSCD

摘要：

To　improve　the　classification　accuracy　of　convolution　neural　network　similar　to　conditional　deep　learning　network　(CDLN),　a　method　of　joint　training　with　multiple　classifiers　was　proposed　in　this　paper.　When　training　the　network,　all　the　error　signals　of　the　classifiers　were　applied　to　update　weights　by　Back　Propagation.　In　the　experiments,　CDLN-L　and　CDLN-A　based　on　LeNet-5　and　AlexNet　were　studied　on　the　MINIST,　CIFAR-100　and　Pascal　Voc　databases,　and　an　increase　of　4.39%　in　classification　accuracy　was　achieved.　The　experiments　demonstrate　that　the　proposed　method　can　improve　the　accuracy　of　the　network　similar　to　CDLN.　©　2018,　Editorial　Department　of　Journal　of　Beijing　University　of　Technology.　All　right　reserved.

关键词：

Classification accuracy; Conditional deep learning network (CDLN); Convolution neural network; Deep learning; Image classification; Joint training by multiple classifiers (JTMC); Multiple classifier

作者机构：

[ 1 ] [Li, J.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 2 ] [Li, J.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 3 ] [Li, L.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 4 ] [Li, L.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 5 ] [Zhang, Y.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 6 ] [Zhang, Y.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 7 ] [Wang, P.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 8 ] [Wang, P.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China
[ 9 ] [Zuo, G.]Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China
[ 10 ] [Zuo, G.]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, 100124, China

通讯作者信息：

[Zuo, G.]Faculty of Information Technology, Beijing University of TechnologyChina

电子邮件地址：

zuoguoyu@bjut.edu.cn

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至